FreeKV: Boosting KV Cache Retrieval for Efficient LLM Inference

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Guangda, Li, Chengwei, Ning, Zhenyu, Lin, Jing, Yao, Yiwu, Ke, Danning, Guo, Minyi, Zhao, Jieru
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911497064546304
author Liu, Guangda
Li, Chengwei
Ning, Zhenyu
Lin, Jing
Yao, Yiwu
Ke, Danning
Guo, Minyi
Zhao, Jieru
author_facet Liu, Guangda
Li, Chengwei
Ning, Zhenyu
Lin, Jing
Yao, Yiwu
Ke, Danning
Guo, Minyi
Zhao, Jieru
contents Large language models (LLMs) are widely deployed with rapidly expanding context windows to support increasingly demanding applications. However, long contexts pose significant deployment challenges, primarily due to the KV cache whose size grows proportionally with context length. While KV cache compression methods have been proposed to address this issue, KV dropping methods incur considerable accuracy loss, and KV retrieval methods suffer from significant efficiency bottlenecks. We propose FreeKV, a training-free algorithm-system co-optimization framework to enhance KV retrieval efficiency while preserving accuracy. On the algorithm side, FreeKV introduces speculative retrieval to shift the KV selection and recall processes out of the critical path, combined with fine-grained correction to ensure accuracy. On the system side, FreeKV employs hybrid KV layouts across CPU and GPU memory to eliminate fragmented data transfers, and leverages double-buffered streamed recall to further improve efficiency, enabling effective overlap with computation, full latency hiding, and practical speedups from speculative recall. Experiments demonstrate that FreeKV achieves near-lossless accuracy across various scenarios and models, delivering up to a 13$\times$ speedup compared to SOTA KV retrieval methods. Code is available at https://github.com/sjtu-zhao-lab/FreeKV.
format Preprint
id arxiv_https___arxiv_org_abs_2505_13109
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FreeKV: Boosting KV Cache Retrieval for Efficient LLM Inference
Liu, Guangda
Li, Chengwei
Ning, Zhenyu
Lin, Jing
Yao, Yiwu
Ke, Danning
Guo, Minyi
Zhao, Jieru
Machine Learning
Artificial Intelligence
Computation and Language
Large language models (LLMs) are widely deployed with rapidly expanding context windows to support increasingly demanding applications. However, long contexts pose significant deployment challenges, primarily due to the KV cache whose size grows proportionally with context length. While KV cache compression methods have been proposed to address this issue, KV dropping methods incur considerable accuracy loss, and KV retrieval methods suffer from significant efficiency bottlenecks. We propose FreeKV, a training-free algorithm-system co-optimization framework to enhance KV retrieval efficiency while preserving accuracy. On the algorithm side, FreeKV introduces speculative retrieval to shift the KV selection and recall processes out of the critical path, combined with fine-grained correction to ensure accuracy. On the system side, FreeKV employs hybrid KV layouts across CPU and GPU memory to eliminate fragmented data transfers, and leverages double-buffered streamed recall to further improve efficiency, enabling effective overlap with computation, full latency hiding, and practical speedups from speculative recall. Experiments demonstrate that FreeKV achieves near-lossless accuracy across various scenarios and models, delivering up to a 13$\times$ speedup compared to SOTA KV retrieval methods. Code is available at https://github.com/sjtu-zhao-lab/FreeKV.
title FreeKV: Boosting KV Cache Retrieval for Efficient LLM Inference
topic Machine Learning
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2505.13109